From 32cf7c3c94623514eb882addae307212c1507239 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 4 Nov 2013 18:05:09 +0100 Subject: locking: Move the percpu-rwsem code to kernel/locking/ Suggested-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-52bjmtty46we26hbfd9sc9iy@git.kernel.org Signed-off-by: Ingo Molnar diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index bdd313a..baab8e5 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -21,4 +21,5 @@ obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o -obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o \ No newline at end of file +obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o +obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c new file mode 100644 index 0000000..652a8ee --- /dev/null +++ b/kernel/locking/percpu-rwsem.c @@ -0,0 +1,165 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +int __percpu_init_rwsem(struct percpu_rw_semaphore *brw, + const char *name, struct lock_class_key *rwsem_key) +{ + brw->fast_read_ctr = alloc_percpu(int); + if (unlikely(!brw->fast_read_ctr)) + return -ENOMEM; + + /* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */ + __init_rwsem(&brw->rw_sem, name, rwsem_key); + atomic_set(&brw->write_ctr, 0); + atomic_set(&brw->slow_read_ctr, 0); + init_waitqueue_head(&brw->write_waitq); + return 0; +} + +void percpu_free_rwsem(struct percpu_rw_semaphore *brw) +{ + free_percpu(brw->fast_read_ctr); + brw->fast_read_ctr = NULL; /* catch use after free bugs */ +} + +/* + * This is the fast-path for down_read/up_read, it only needs to ensure + * there is no pending writer (atomic_read(write_ctr) == 0) and inc/dec the + * fast per-cpu counter. The writer uses synchronize_sched_expedited() to + * serialize with the preempt-disabled section below. + * + * The nontrivial part is that we should guarantee acquire/release semantics + * in case when + * + * R_W: down_write() comes after up_read(), the writer should see all + * changes done by the reader + * or + * W_R: down_read() comes after up_write(), the reader should see all + * changes done by the writer + * + * If this helper fails the callers rely on the normal rw_semaphore and + * atomic_dec_and_test(), so in this case we have the necessary barriers. + * + * But if it succeeds we do not have any barriers, atomic_read(write_ctr) or + * __this_cpu_add() below can be reordered with any LOAD/STORE done by the + * reader inside the critical section. See the comments in down_write and + * up_write below. + */ +static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val) +{ + bool success = false; + + preempt_disable(); + if (likely(!atomic_read(&brw->write_ctr))) { + __this_cpu_add(*brw->fast_read_ctr, val); + success = true; + } + preempt_enable(); + + return success; +} + +/* + * Like the normal down_read() this is not recursive, the writer can + * come after the first percpu_down_read() and create the deadlock. + * + * Note: returns with lock_is_held(brw->rw_sem) == T for lockdep, + * percpu_up_read() does rwsem_release(). This pairs with the usage + * of ->rw_sem in percpu_down/up_write(). + */ +void percpu_down_read(struct percpu_rw_semaphore *brw) +{ + might_sleep(); + if (likely(update_fast_ctr(brw, +1))) { + rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 0, _RET_IP_); + return; + } + + down_read(&brw->rw_sem); + atomic_inc(&brw->slow_read_ctr); + /* avoid up_read()->rwsem_release() */ + __up_read(&brw->rw_sem); +} + +void percpu_up_read(struct percpu_rw_semaphore *brw) +{ + rwsem_release(&brw->rw_sem.dep_map, 1, _RET_IP_); + + if (likely(update_fast_ctr(brw, -1))) + return; + + /* false-positive is possible but harmless */ + if (atomic_dec_and_test(&brw->slow_read_ctr)) + wake_up_all(&brw->write_waitq); +} + +static int clear_fast_ctr(struct percpu_rw_semaphore *brw) +{ + unsigned int sum = 0; + int cpu; + + for_each_possible_cpu(cpu) { + sum += per_cpu(*brw->fast_read_ctr, cpu); + per_cpu(*brw->fast_read_ctr, cpu) = 0; + } + + return sum; +} + +/* + * A writer increments ->write_ctr to force the readers to switch to the + * slow mode, note the atomic_read() check in update_fast_ctr(). + * + * After that the readers can only inc/dec the slow ->slow_read_ctr counter, + * ->fast_read_ctr is stable. Once the writer moves its sum into the slow + * counter it represents the number of active readers. + * + * Finally the writer takes ->rw_sem for writing and blocks the new readers, + * then waits until the slow counter becomes zero. + */ +void percpu_down_write(struct percpu_rw_semaphore *brw) +{ + /* tell update_fast_ctr() there is a pending writer */ + atomic_inc(&brw->write_ctr); + /* + * 1. Ensures that write_ctr != 0 is visible to any down_read/up_read + * so that update_fast_ctr() can't succeed. + * + * 2. Ensures we see the result of every previous this_cpu_add() in + * update_fast_ctr(). + * + * 3. Ensures that if any reader has exited its critical section via + * fast-path, it executes a full memory barrier before we return. + * See R_W case in the comment above update_fast_ctr(). + */ + synchronize_sched_expedited(); + + /* exclude other writers, and block the new readers completely */ + down_write(&brw->rw_sem); + + /* nobody can use fast_read_ctr, move its sum into slow_read_ctr */ + atomic_add(clear_fast_ctr(brw), &brw->slow_read_ctr); + + /* wait for all readers to complete their percpu_up_read() */ + wait_event(brw->write_waitq, !atomic_read(&brw->slow_read_ctr)); +} + +void percpu_up_write(struct percpu_rw_semaphore *brw) +{ + /* release the lock, but the readers can't use the fast-path */ + up_write(&brw->rw_sem); + /* + * Insert the barrier before the next fast-path in down_read, + * see W_R case in the comment above update_fast_ctr(). + */ + synchronize_sched_expedited(); + /* the last writer unblocks update_fast_ctr() */ + atomic_dec(&brw->write_ctr); +} diff --git a/lib/Makefile b/lib/Makefile index ca8cadc..8d3c629 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -42,7 +42,6 @@ obj-$(CONFIG_GENERIC_PCI_IOMAP) += pci_iomap.o obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o obj-$(CONFIG_CHECK_SIGNATURE) += check_signature.o obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o -lib-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS)) obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o diff --git a/lib/percpu-rwsem.c b/lib/percpu-rwsem.c deleted file mode 100644 index 652a8ee..0000000 --- a/lib/percpu-rwsem.c +++ /dev/null @@ -1,165 +0,0 @@ -#include -#include -#include -#include -#include -#include -#include -#include -#include - -int __percpu_init_rwsem(struct percpu_rw_semaphore *brw, - const char *name, struct lock_class_key *rwsem_key) -{ - brw->fast_read_ctr = alloc_percpu(int); - if (unlikely(!brw->fast_read_ctr)) - return -ENOMEM; - - /* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */ - __init_rwsem(&brw->rw_sem, name, rwsem_key); - atomic_set(&brw->write_ctr, 0); - atomic_set(&brw->slow_read_ctr, 0); - init_waitqueue_head(&brw->write_waitq); - return 0; -} - -void percpu_free_rwsem(struct percpu_rw_semaphore *brw) -{ - free_percpu(brw->fast_read_ctr); - brw->fast_read_ctr = NULL; /* catch use after free bugs */ -} - -/* - * This is the fast-path for down_read/up_read, it only needs to ensure - * there is no pending writer (atomic_read(write_ctr) == 0) and inc/dec the - * fast per-cpu counter. The writer uses synchronize_sched_expedited() to - * serialize with the preempt-disabled section below. - * - * The nontrivial part is that we should guarantee acquire/release semantics - * in case when - * - * R_W: down_write() comes after up_read(), the writer should see all - * changes done by the reader - * or - * W_R: down_read() comes after up_write(), the reader should see all - * changes done by the writer - * - * If this helper fails the callers rely on the normal rw_semaphore and - * atomic_dec_and_test(), so in this case we have the necessary barriers. - * - * But if it succeeds we do not have any barriers, atomic_read(write_ctr) or - * __this_cpu_add() below can be reordered with any LOAD/STORE done by the - * reader inside the critical section. See the comments in down_write and - * up_write below. - */ -static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val) -{ - bool success = false; - - preempt_disable(); - if (likely(!atomic_read(&brw->write_ctr))) { - __this_cpu_add(*brw->fast_read_ctr, val); - success = true; - } - preempt_enable(); - - return success; -} - -/* - * Like the normal down_read() this is not recursive, the writer can - * come after the first percpu_down_read() and create the deadlock. - * - * Note: returns with lock_is_held(brw->rw_sem) == T for lockdep, - * percpu_up_read() does rwsem_release(). This pairs with the usage - * of ->rw_sem in percpu_down/up_write(). - */ -void percpu_down_read(struct percpu_rw_semaphore *brw) -{ - might_sleep(); - if (likely(update_fast_ctr(brw, +1))) { - rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 0, _RET_IP_); - return; - } - - down_read(&brw->rw_sem); - atomic_inc(&brw->slow_read_ctr); - /* avoid up_read()->rwsem_release() */ - __up_read(&brw->rw_sem); -} - -void percpu_up_read(struct percpu_rw_semaphore *brw) -{ - rwsem_release(&brw->rw_sem.dep_map, 1, _RET_IP_); - - if (likely(update_fast_ctr(brw, -1))) - return; - - /* false-positive is possible but harmless */ - if (atomic_dec_and_test(&brw->slow_read_ctr)) - wake_up_all(&brw->write_waitq); -} - -static int clear_fast_ctr(struct percpu_rw_semaphore *brw) -{ - unsigned int sum = 0; - int cpu; - - for_each_possible_cpu(cpu) { - sum += per_cpu(*brw->fast_read_ctr, cpu); - per_cpu(*brw->fast_read_ctr, cpu) = 0; - } - - return sum; -} - -/* - * A writer increments ->write_ctr to force the readers to switch to the - * slow mode, note the atomic_read() check in update_fast_ctr(). - * - * After that the readers can only inc/dec the slow ->slow_read_ctr counter, - * ->fast_read_ctr is stable. Once the writer moves its sum into the slow - * counter it represents the number of active readers. - * - * Finally the writer takes ->rw_sem for writing and blocks the new readers, - * then waits until the slow counter becomes zero. - */ -void percpu_down_write(struct percpu_rw_semaphore *brw) -{ - /* tell update_fast_ctr() there is a pending writer */ - atomic_inc(&brw->write_ctr); - /* - * 1. Ensures that write_ctr != 0 is visible to any down_read/up_read - * so that update_fast_ctr() can't succeed. - * - * 2. Ensures we see the result of every previous this_cpu_add() in - * update_fast_ctr(). - * - * 3. Ensures that if any reader has exited its critical section via - * fast-path, it executes a full memory barrier before we return. - * See R_W case in the comment above update_fast_ctr(). - */ - synchronize_sched_expedited(); - - /* exclude other writers, and block the new readers completely */ - down_write(&brw->rw_sem); - - /* nobody can use fast_read_ctr, move its sum into slow_read_ctr */ - atomic_add(clear_fast_ctr(brw), &brw->slow_read_ctr); - - /* wait for all readers to complete their percpu_up_read() */ - wait_event(brw->write_waitq, !atomic_read(&brw->slow_read_ctr)); -} - -void percpu_up_write(struct percpu_rw_semaphore *brw) -{ - /* release the lock, but the readers can't use the fast-path */ - up_write(&brw->rw_sem); - /* - * Insert the barrier before the next fast-path in down_read, - * see W_R case in the comment above update_fast_ctr(). - */ - synchronize_sched_expedited(); - /* the last writer unblocks update_fast_ctr() */ - atomic_dec(&brw->write_ctr); -} -- cgit v0.10.2